Machine Translation on WMT 19 (PRR)
66PRRLookBackLens
Evaluation Results
| Method | Links | |
|---|---|---|
| LookBackLensBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 66 | |
| MINDBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 64.1 | |
| SheepsBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 64 | |
| SAPLMABackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 63.1 | |
| TADBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 62.3 | |
| LookBackLensBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 61.3 | |
| TADBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 59.2 | |
| TADBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 55.3 | |
| SAPLMABackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 54.8 | |
| LookBackLensBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 53.9 | |
| SATRMDBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 52.5 | |
| SATRMDBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 52.5 | |
| Simple FocusBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 52.1 | |
| SheepsBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 50.9 | |
| Simple FocusBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 49.6 | |
| SheepsBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 48.7 | |
| MSPBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 48.4 | |
| Mean Token EntropyBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 47.5 | |
| SATRMDBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 47.5 | |
| Simple FocusBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 47.2 | |
| PerplexityBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 46.6 | |
| FocusBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 46.5 | |
| MSPBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 45.9 | |
| SARBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 45.5 | |
| Mean Token EntropyBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 45.3 | |
| FocusBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 45.2 | |
| MSPBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 45.1 | |
| MINDBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 45.1 | |
| PerplexityBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 44.9 | |
| SARBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 44.5 | |
| SARBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 43.5 | |
| Mean Token EntropyBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 42.5 | |
| PerplexityBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 41.6 | |
| FocusBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 41.6 | |
| Lexical Similarity Rouge-LBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 40.4 | |
| Lexical Similarity Rouge-LBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 40.3 | |
| Semantic EntropyBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 40.1 | |
| CCPBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 38.8 | |
| Semantic EntropyBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 37.9 | |
| EigenScoreBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 37.4 | |
| Lexical Similarity Rouge-LBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 37 | |
| CCPBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 36.9 | |
| Ecc. NLI Score entail.Backbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 36.8 | |
| Semantic EntropyBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 36.6 | |
| MINDBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 36.5 | |
| CCPBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 36.3 | |
| Semantic DensityBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 35.8 | |
| SAPLMABackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 34.5 | |
| Ecc. NLI Score entail.Backbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 34.3 | |
| Ecc. NLI Score entail.Backbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 34 | |
| DegMat NLI Score entail.Backbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 33.2 | |
| EigenScoreBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 31.8 | |
| Semantic DensityBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 31.3 | |
| DegMat NLI Score entail.Backbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 31.2 | |
| EVL NLI Score entail.Backbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 30.2 | |
| Semantic DensityBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 29.5 | |
| EVL NLI Score entail.Backbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 29.4 | |
| DegMat NLI Score entail.Backbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 28.5 | |
| LUQBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 27.6 | |
| LUQBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 26.5 | |
| EVL NLI Score entail.Backbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 25.2 | |
| EigenScoreBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 24.9 | |
| LUQBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 22.4 | |
| FactoscopeBackbone=Llama-3.1 8b, Correctness Metric=Comet2024.08 | 12 | |
| FactoscopeBackbone=Qwen-2.5 7b, Reference Quality Metric=Comet2024.08 | 6.9 | |
| FactoscopeBackbone=Gemma-2 9b, Reference Quality Metric=Comet2024.08 | 2.1 |